Artificial Intelligence Software for Document Quality Inspection

2. The method of claim 1, wherein the one or more artifact types include at least one of (i) horizontal banding, (ii) vertical misalignment or banding, (iii) incorrect or missing colors, (iv) blurriness or smearing, or (v) marking produced by a roller of the printer.

3. The method of claim 1, wherein the output information relating to the one or more artifacts detected by the model is output as probabilities that the one or more artifacts detected by the model in the test images are associated with each of the one or more artifact types.

4. The method of claim 3, wherein the probabilities are output as a vector wherein components of the vector include a probability associated with each of the one or more artifact types.

6. The method of claim 1, wherein processing the differences between each noised image and the reference image included in the noised image includes measuring pixel-wise differences between each noised image and the reference image included in the noised image.

7. The method of claim 1, wherein processing the differences between each noised image and the reference image included in the noised image includes registering each noised image and the reference image included in the noised image so that the differences are associated with the artifact in the noised image.

8. The method of claim 1, wherein the model is a convolutional neural network model.

10. The system of claim 9, wherein the one or more artifact types include at least one of (i) horizontal banding, (ii) vertical misalignment or banding, (iii) incorrect or missing colors, (iv) blurriness or smearing, or (v) marking produced by a roller of the printer.

12. The system of claim 9, wherein the model processes the differences between each noised image and the reference image included in the noised image by measuring pixel-wise differences between each noised image and the reference image included in the noised image.

13. The system of claim 9, wherein the model processes the differences between each noised image and the reference image included in the noised image by registering each noised image and the reference image included in the noised image so that the differences are associated with the artifact in the noised image.

14. The system of claim 9, wherein the model is a convolutional neural network model.

16. The non-transitory computer-readable storage media of claim 15, wherein the one or more artifact types include at least one of (i) horizontal banding, (ii) vertical misalignment or banding, (iii) incorrect or missing colors, (iv) blurriness or smearing, or (v) marking produced by a roller of the printer.

18. The non-transitory computer-readable storage media of claim 15, wherein the model processes the differences between each noised image and the reference image included in the noised image by measuring pixel-wise differences between each noised image and the reference image included in the noised image.

19. The non-transitory computer-readable storage media of claim 15, wherein the model processes the differences between each noised image and the reference image included in the noised image by registering each noised image and the reference image included in the noised image so that the differences are associated with the artifact in the noised image.

20. The non-transitory computer-readable storage media of claim 15, wherein the model is a convolutional neural network model.